Pair

Qwen3.8-27B

Name: OpenWeights Terminal measured pairs
Creator: Dvidia
License: https://owterminal.com/cite

One quoted capture. Rank only lives inside a filter.

M6 mini 32GB · 4-bit · TensorFold

Decode · tok/s

61.9

Prefill

—

tok/100W

229.3

Qwen3.8-27B (MLX 4-bit, DFlash2 drafting) on a 32 GB Mac mini M6: code 10.1 → 61.9 tok/s (6.1×) · chat 10.1 → 30.8 tok/s (3.0×)

Rank is the quoted code 61.9. Chat 30.8 stays in the note.

Officialclaimed